Text-to-speech for the hearing impaired
arXiv:2012.02174
Abstract
Text-to-speech (TTS) systems offer the opportunity to compensate for a hearing loss at the source rather than correcting for it at the receiving end. This removes limitations such as time constraints for algorithms that amplify a sound in a hearing aid and can lead to higher speech quality. We propose an algorithm that restores loudness to normal perception at a high resolution in time, frequency and level, and embed it in a TTS system that uses Tacotron2 and WaveGlow to produce individually amplified speech. Subjective evaluations of speech quality showed that the proposed algorithm led to high-quality audio with sound quality similar to original or linearly amplified speech but considerably higher speech intelligibility in noise. Transfer learning led to a quick adaptation of the produced spectra from original speech to individually amplified speech, resulted in high speech quality and intelligibility, and thus gives us a way to train an individual TTS system efficiently.
References in corpus (6)
- Variational Inference with Normalizing Flows
- SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
- MelNet: A Generative Model for Audio in the Frequency Domain
- Adversarial Audio Synthesis
- Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
- SqueezeWave: Extremely Lightweight Vocoders for On-device Speech Synthesis